Citance-Contextualized Summarization of Scientific Papers

Shahbaz Syed, Ahmad Dawar Hakimi, Khalid Al-Khatib, Martin Potthast
11/4/2023
cs.CL

No official code found. Best implementation: webis-de/EMNLP-23 (6 stars, last commit 2023-11-30).

Abstract

Current approaches to automatic summarization of scientific papers generate informative summaries in the form of abstracts. However, abstracts are not intended to show the relationship between a paper and the references cited in it. We propose a new contextualized summarization approach that can generate an informative summary conditioned on a given sentence containing the citation of a reference (a so-called "citance"). This summary outlines the content of the cited paper relevant to the citation location. Thus, our approach extracts and models the citances of a paper, retrieves relevant passages from cited papers, and generates abstractive summaries tailored to each citance. We evaluate our approach using $\textbf{Webis-Context-SciSumm-2023}$, a new dataset containing 540K~computer science papers and 4.6M~citances therein.

View on arXivView PDF

Code Implementations(1)

webis-de/EMNLP-23Community100%
60Oct 12, 20232 years ago

Similar Papers

Cite this paper

@article{syed2023citancecontextualized,
  title  = {Citance-Contextualized Summarization of Scientific Papers},
  author = {Shahbaz Syed and Ahmad Dawar Hakimi and Khalid Al-Khatib and Martin Potthast},
  year   = {2023},
  eprint = {2311.02408},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.02408v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.02408.svg)](https://codeofpaper.com/paper/2311.02408)

Discussion